Re: [PATCH V2] x86 spinlock: Fix memory corruption on completing completions

[Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>]

Ccing Davidlohr, (sorry that I got confused with similar address in cc
list).

On 02/09/2015 08:44 PM, Oleg Nesterov wrote:
> On 02/09, Raghavendra K T wrote:
>>
>> +static inline void __ticket_check_and_clear_slowpath(arch_spinlock_t *lock)
>> +{
>> +	arch_spinlock_t old, new;
>> +	__ticket_t diff;
>> +
>> +	old.tickets = READ_ONCE(lock->tickets);
>> +	diff = (old.tickets.tail & ~TICKET_SLOWPATH_FLAG) - old.tickets.head;
>> +
>> +	/* try to clear slowpath flag when there are no contenders */
>> +	if ((old.tickets.tail & TICKET_SLOWPATH_FLAG) &&
>> +		(diff == TICKET_LOCK_INC)) {
>> +		new = old;
>> +		new.tickets.tail &= ~TICKET_SLOWPATH_FLAG;
>> +		cmpxchg(&lock->head_tail, old.head_tail, new.head_tail);
>> +	}
>> +}
>
> Can't we simplify it? We own .head, and we already know it. We only need
> to clear TICKET_SLOWPATH_FLAG in .tail atomically?
>
> IOW,
>
> 	static inline void __ticket_check_and_clear_slowpath(arch_spinlock_t *lock, __ticket_t head)
> 	{
> 		__ticket_t old_tail, new_tail;
>
> 		new_tail = head + TICKET_LOCK_INC;
> 		old_tail = new_tail | TICKET_SLOWPATH_FLAG;
>
> 		if (READ_ONCE(lock->tickets.tail) == old_tail)
> 			cmpxchg(&lock->tickets.tail, old_tail, new_tail);
> 	}
>
> Plus
>
> 	-	__ticket_check_and_clear_slowpath(lock);
> 	+	__ticket_check_and_clear_slowpath(lock, inc.tail);
>
> Or I missed something?

Thanks.. Perfect, 'll update with this change. (Jeremy had hinted
similar).

>
> And I think it would be better to avoid ifdef(CONFIG_PARAVIRT_SPINLOCKS),
> ww can just do
>
> 	if (TICKET_SLOWPATH_FLAG)
> 		__ticket_check_and_clear_slowpath();
>

Okay.
While at it, I think current arch_spin_unlock() has similar structure
and wanted to clean it up. considering we define
TICKET_SLOWPATH_FLAG 0 or 1, I think compiler would be smart enough
to generate appropriate code and we could avoid #ifdef.